Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910217658171392 |
|---|---|
| author | Zhang, Hai-Feng Chen, Zhao-Yun Wang, Peng Guo, Liang-Liang Wang, Tian-Le Yang, Xiao-Yan Zhao, Ren-Ze Zhao, Ze-An Zhang, Sheng Du, Lei Tao, Hao-Ran Jia, Zhi-Long Kong, Wei-Cheng Liu, Huan-Yu Vasilakos, Athanasios V. Yang, Yang Wu, Yu-Chun Guan, Ji Duan, Peng Guo, Guo-Ping |
| author_facet | Zhang, Hai-Feng Chen, Zhao-Yun Wang, Peng Guo, Liang-Liang Wang, Tian-Le Yang, Xiao-Yan Zhao, Ren-Ze Zhao, Ze-An Zhang, Sheng Du, Lei Tao, Hao-Ran Jia, Zhi-Long Kong, Wei-Cheng Liu, Huan-Yu Vasilakos, Athanasios V. Yang, Yang Wu, Yu-Chun Guan, Ji Duan, Peng Guo, Guo-Ping |
| contents | Quantum machine learning (QML) models, like their classical counterparts, are vulnerable to adversarial attacks, hindering their secure deployment. Here, we report the first systematic experimental robustness benchmark for 20-qubit quantum neural network (QNN) classifiers executed on a superconducting processor. Our benchmarking framework features an efficient adversarial attack algorithm designed for QNNs, enabling quantitative characterization of adversarial robustness and robustness bounds. From our analysis, we verify that adversarial training reduces sensitivity to targeted perturbations by regularizing input gradients, significantly enhancing QNN's robustness. Additionally, our analysis reveals that QNNs exhibit superior adversarial robustness compared to classical neural networks, an advantage attributed to inherent quantum noise. Furthermore, the empirical upper bound extracted from our attack experiments shows a minimal deviation ($3 \times 10^{-3}$) from the theoretical lower bound, providing strong experimental confirmation of the attack's effectiveness and the tightness of fidelity-based robustness bounds. This work establishes a critical experimental framework for assessing and improving quantum adversarial robustness, paving the way for secure and reliable QML applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16714 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor Zhang, Hai-Feng Chen, Zhao-Yun Wang, Peng Guo, Liang-Liang Wang, Tian-Le Yang, Xiao-Yan Zhao, Ren-Ze Zhao, Ze-An Zhang, Sheng Du, Lei Tao, Hao-Ran Jia, Zhi-Long Kong, Wei-Cheng Liu, Huan-Yu Vasilakos, Athanasios V. Yang, Yang Wu, Yu-Chun Guan, Ji Duan, Peng Guo, Guo-Ping Quantum Physics Machine Learning Quantum machine learning (QML) models, like their classical counterparts, are vulnerable to adversarial attacks, hindering their secure deployment. Here, we report the first systematic experimental robustness benchmark for 20-qubit quantum neural network (QNN) classifiers executed on a superconducting processor. Our benchmarking framework features an efficient adversarial attack algorithm designed for QNNs, enabling quantitative characterization of adversarial robustness and robustness bounds. From our analysis, we verify that adversarial training reduces sensitivity to targeted perturbations by regularizing input gradients, significantly enhancing QNN's robustness. Additionally, our analysis reveals that QNNs exhibit superior adversarial robustness compared to classical neural networks, an advantage attributed to inherent quantum noise. Furthermore, the empirical upper bound extracted from our attack experiments shows a minimal deviation ($3 \times 10^{-3}$) from the theoretical lower bound, providing strong experimental confirmation of the attack's effectiveness and the tightness of fidelity-based robustness bounds. This work establishes a critical experimental framework for assessing and improving quantum adversarial robustness, paving the way for secure and reliable QML applications. |
| title | Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2505.16714 |